Classification of Occluded Objects using Fast Recurrent Processing

TL;DR

This paper introduces a computationally efficient framework that enhances feedforward neural networks with recurrent processing to improve occluded object classification, achieving significant accuracy gains without high computational costs.

Contribution

It proposes a novel method to incorporate recurrent-like iterative processing into feedforward networks, improving occlusion handling in computer vision tasks.

Findings

Achieves 2x improvement in classification accuracy for occluded objects.

Outperforms Restricted Boltzmann Machines in occlusion scenarios.

Demonstrates efficient recurrent processing without high computational demands.

Abstract

Recurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset, and shown to achieve 2$\times$ improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.